Global nearest neighbor (gnn) based target tracking and data association

Abstract

A modified GNN/DA subsystem processes angle only measurements from at least two sensors (but can be replicated to n sensors using a similar track fusion framework per sensor as a local track center and then fusing them via a multiple local track fusion architecture) to reconstruct a complete battle space picture consisting of multiple moving targets. In some cases, the sensor is an EO/IR camera and the moving targets are UAVs. The modified GNN/DA is used as part of a Fire Control Solution (FCS) either implemented on a ground-based vehicle or on-board a projectile.

What is claimed: 
     
         1 . An improved multiple target detection and tracking (MTT) system comprising:
 two or more sensors, each sensor located on a ground based vehicle such that the two or more sensors are configured to capture angle only measurements for a ground to air mission using a modified global nearest neighbor/data association (GNN/DA) algorithm, the modified GNN/DA comprising:   a data association (DA) scheme to pair individual sets of angle only measurements from individual targets detected by individual sensors using an Extended Kalman Filter (EKF) of individual target state estimators (TSE) residing in a track file management (TFM) module of each ground based vehicle;   an interface between output from the TFM and a fire control system (FCS) guidance subsystem and a weapon to target assignment (WTA) module for engagement of multiple weapons with multiple individual targets;   each sensor having an on-board multiple target detection and tracking (MTT), data association (DA), and track file management (TFM) system installed thereon, wherein the multiple target detection and tracking (MTT), data association (DA), and track file management (TFM) system are configured to direct the following operations to deliver one or more correct track files to the guidance subsystem to complete an engagement:
 process images from the two or more sensors on each of the two or more ground vehicles in real-time; 
 detect one or more target location measurements for one or more individual targets using the images from the two or more sensors each on one of the two or more ground vehicles to produce potential target tracks; 
 process the one or more target location measurements to determine if the one or more target location measurements from the two or more sensors each on one of the two or more vehicles are correlated with predicted target tracks via the fire control system, if not, then uncorrelated target tracks are placed in a separate file for possible new target track initiation/creation; 
 associate the potential target tracks via a gating system, wherein potential target tracks falling within a gating threshold are chosen as active target tracks; 
 update and maintain active target tracks as part of the track file management (TFM) system, as target state estimates for the multiple individual targets; and 
 feed output from the track file management (TFM) system to the weapon target assignment (WTA) system to guide each of the multiple weapons onto a collision course with one of the one or more targets by pairing the correct active target track with correct one or more targets. 
   
     
     
         2 . The improved multiple target detection and tracking (MTT) system according to  claim 1 , wherein the two or more sensors are EO/IR cameras. 
     
     
         3 . The improved multiple target detection and tracking (MTT) system according to  claim 1 , wherein the ground based vehicle is a tank. 
     
     
         4 . The improved multiple target detection and tracking (MTT) system according to  claim 1 , wherein if active target tracks created in the track file management (TFM) system have not received continuous measurement updates for more than three consecutive samples, the tracks are deleted. 
     
     
         5 . The improved multiple target detection and tracking (MTT) system according to  claim 1 , wherein an active track file management (TFM) system contains all active target tracks. 
     
     
         6 . A method of data association in a multi-weapon/multi target system, comprising:
 processing images from at least one sensor mounted on a ground based vehicle in real-time, wherein there are two or more vehicles and each sensor is part of a fire control subsystem (FCS), the at least one sensor having an on-board multiple target detection and tracking (MTT), data association (DA), and track file management (TFM) system installed thereon, wherein the multiple target detection and tracking (MTT), data association (DA), and track file management (TFM) system are configured to direct the following operations to deliver one or more correct track files to a guidance subsystem to complete an engagement;   detecting one or more target location measurements for one or more individual targets using the images from the at least one sensor to produce potential target tracks;   processing the one or more target location measurements to determine if the one or more target location measurements from the at least one sensor are correlated with predicted target tracks via the fire control system, if not, then uncorrelated target tracks are placed in a separate file for possible new target track initiation/creation;   associating the potential target tracks via a gating system, wherein the potential target tracks that fall within a gating threshold are chosen as active target tracks;   updating and maintaining the active target tracks as part of the track file management (TFM) system, as target state estimates for the individual targets;   feeding output from the track file management (TFM) system to a weapon target assignment system (WTA);   pairing an active target track with a correct individual target; and   feeding output from the track file management (TFM) system to the weapon target assignment (WTA) system to guide multiple weapons onto a collision course with respective multiple individual targets by pairing the correct active target track with the correct individual targets.   
     
     
         7 . The method of data association in a multi-projectile/multi target system according to  claim 6 , wherein the at least one sensor is an EO/IR camera. 
     
     
         8 . The method of data association in a multi-projectile/multi target system according to  claim 6 , wherein the ground based vehicle is a tank. 
     
     
         9 . The method of data association in a multi-projectile/multi target system according to  claim 6 , wherein uncorrelated target tracks are declared as clutters and no new track is initiated or created if new target location measurements do not persist across continuous samples. 
     
     
         10 . The method of data association in a multi-projectile/multi target system according to  claim 6 , wherein if active target tracks created in the track file management (TFM) system have not received continuous measurement updates for more than three consecutive samples, the tracks are deleted.